Score your question before you research it

HiExplore scores any question 0–100 across six dimensions — verifiability, depth, scarcity, social value, innovation, feasibility. Below 60? Don't research it yet. Above? A team of AI agents breaks it into a question tree and explores it for days — every claim must carry a falsifiable hypothesis, and when the AI gets stuck, it asks real humans through your phone.

No signup to tryMIT-licensedData stays localBYO model (DeepSeek / Qwen / Claude / Ollama)
[ Screenshot placeholder: QVS score card — 78 / grade B / six-axis radar ]

You don't need better answers. You need better questions.

Most "this seems interesting" questions die on verifiability and feasibility. Finding out costs you 10 seconds instead of three weeks.

❌ “Will AI replace programmers?”

Unfalsifiable, answered a thousand times, no way to know you were right.

55 — don't bother

✅ “Across 3 real codebases, how did Copilot change median PR review time and defect escape rate?”

Checkable, specific, nobody has published it.

82 — promote it

Four steps, from question to conclusions

STEP 1

Ask

Drop in the question you actually want answered — or pick one from the question board.

STEP 2

Score

QVS returns a 0–100 score with a radar breakdown and sharpening suggestions. Below 60, it tells you not to bother yet.

STEP 3

Agent team explores

5–8 directions → specialized agents (researcher, analyst, reviewer…) → loop of decompose → execute → review → record, producing falsifiable hypotheses, notes, and simulations.

STEP 4

Reality feedback loop

When the AI hits a question only reality can answer, it's pushed to real humans via a companion phone app. Decision timeline can replay any branch.

vs generic AI search / Deep Research

Generic AI search / Deep ResearchHiExplore
Question value gate✗ answers everything✓ QVS 6-dim score, <60 = don't bother
Claim reliabilitylooks rightevery node requires a falsifiable hypothesis; reasoning ≠ evidence
Simulation vs realityblendedsimulations explicitly marked "not evidence", with reality check + probe hint
Stuck?keeps hallucinatingpushes the question to real humans / real data (phone app)
Your dataplatform cloudyour browser / local Markdown, Obsidian-friendly
Modelslocked inbring your own: DeepSeek, Qwen, Claude, local Ollama
CodeclosedMIT, self-hostable

Who it's for

🎓 Researchers & grad students

Decompose a big question into verifiable sub-questions; an agent team grinds 24/7 while you make the calls.

✍️ Content creators

Run every topic idea through QVS before investing; exploration notes become your content library.

🧠 Lifelong learners

Turn "things I want to understand" into long-running research projects with a personal knowledge graph.

Your data & models, your rules

🔒 Local-first

Data lives in your browser or local Markdown (Obsidian-friendly). Export a note or the whole vault as a zip.

🧠 Bring your own model

Fully local with Ollama (data never leaves your machine), or any OpenAI-compatible endpoint — DeepSeek, Qwen, Claude.

🛡️ Optional key proxy

Hide your API key behind a serverless function so it never reaches the browser.

🔌 Can touch the physical world

Register HTTP-API devices (sensors, robot arms) — agents read from and act on them mid-exploration, with an auditable call log.

Pricing

Free

No signup required
  • 5 explorations/day anonymous; 30/day logged in
  • BYO model = unlimited
  • Local data + Markdown export

Long-term Exploration membership

Subscription
  • Long-running projects with 24/7 agent teams
  • Higher quotas / advanced models
  • Reality-feedback push quota
  • Supports independent development

FAQ

Do I need an account?

No — try it without signing up. Login (WeChat or email) gives persistence and a higher daily quota.

Where does my data go?

By default it stays in your browser / local files. Only aggregate stats (active time, token usage) are synced to the cloud.

Which models can I use?

Any OpenAI-compatible endpoint: DeepSeek, Qwen, Claude, or fully local via Ollama/LM Studio. A desktop app is recommended for local models.

How is this different from NotebookLM / Perplexity / Deep Research?

They're better at answering; HiExplore is about whether a question deserves answering, and keeping claims falsifiable and checked against reality. You can even run their reports through HiExplore as an audit.

Is it open source?

Yes — MIT, self-hostable, no backend required. github.com/chenhaiyan123/ai-auto-explorer